Context / RAG for AI coding
Every context / rag option Flowpicker tracks, with pricing, setup notes, and compatibility for each.
- None (vanilla) — Simple projects where the LLM context window is sufficient
- @codebase (Cursor) — Zero-config semantic search across a codebase inside Cursor
- Continue codebase indexing — Local-first codebase indexing for use with any model
- Greptile — Cloud-hosted codebase indexing with semantic and code-aware search
- Local ChromaDB — DIY local embedding-based codebase search with full control
- Sourcegraph Cody Context — Cross-repo code search and context for large organizations with Sourcegraph backend
- GitHub Copilot codebase indexing — Zero-config repo indexing natively integrated with GitHub Copilot chat and completions
- Pinecone — Managed vector database for production-scale RAG and semantic code search
- Qdrant — Open-source vector DB with self-hosted and cloud options for codebase RAG
- Weaviate — Hybrid vector + keyword search with built-in vectorization for codebase RAG
- LanceDB — Serverless embedded vector DB, zero-setup local codebase RAG for desktop apps
- Windsurf codebase indexing — Zero-config codebase indexing natively integrated with Windsurf Cascade agent
- pgvector — Vector search inside an existing PostgreSQL database; no new infra required
- Milvus — Billion-scale vector indexing for production RAG; self-hosted or Zilliz Cloud managed
- Redis Vector Search — Sub-millisecond vector search for real-time RAG; ideal for teams already on Redis
- Mem0 — Long-term agent memory and multi-session context continuity across conversations
- turbopuffer — Cheap, fast object-storage-backed vector + full-text search for AI agents at scale
- Vespa — Production-grade hybrid search (vector + BM25 + ranking) at billions-of-docs scale
- Elasticsearch (Vector) — Adding vector search to existing Elastic deployments with hybrid BM25 + ANN
- MongoDB Atlas Vector Search — Vector RAG on top of an existing MongoDB Atlas operational database
- Supabase Vector — Postgres-native vector RAG that piggybacks on Supabase Auth, Storage, and Realtime
- Marqo — End-to-end vector search with built-in embedding generation and tensor pipelines
- Cognee — Open-source memory framework that builds knowledge graphs over agent state and code
- Letta — Stateful agents with self-editing long-term memory built on the MemGPT pattern
- Zep — Memory layer purpose-built for chat agents with temporal knowledge graphs and dedupe
- Augment Context Engine — Enterprise-scale codebase context (200K+ files) with low-latency retrieval and PII filtering
- CocoIndex — Open-source incremental data flow indexing for codebases and docs with real-time updates
- Sweep Index — Codebase context engine tuned for AI PR generation and code modification